Skip to main content
SpringerLink
Log in

Volumetric Representation of Semantically Segmented Human Body Parts Using Superquadrics

  • Conference paper
  • First Online:
Virtual Reality and Augmented Reality (EuroVR 2019)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 11883))

Included in the following conference series:

Abstract

Superquadrics are one of the ideal shape representations for adapting various kinds of primitive shapes with a single equation. This paper revisits the task of representing a 3D human body with multiple superquadrics. As a single superquadric surface can only represent symmetric primitive shapes, we present a method that segments the human body into body parts to estimate their superquadric parameters. Moreover, we propose a novel initial parameter estimation method by using 3D skeleton joints. The results show that superquadric parameters are estimated, which represent human body parts volumetrically.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 74.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Abelha, P., Guerin, F.: Learning how a tool affords by simulating 3D models from the web. In: IEEE/RSJ IROS, pp. 4923–4929, September 2017

    Google Scholar 

  2. Afanasyev, I., et al.: 3D human body pose estimation by superquadrics. In: VISAPP, vol. 2, January 2012

    Google Scholar 

  3. Bardinet, E., Cohen, L.D., Ayache, N.: A parametric deformable model to fit unstructured 3D data. Comput. Vis. Image Underst. 71(1), 39–54 (1998)

    Article  Google Scholar 

  4. Barr, A.H.: Superquadrics and angle-preserving transformations. IEEE Comput. Graph. Appl. 1(1), 11–23 (1981)

    Article  MathSciNet  Google Scholar 

  5. Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR (2017)

    Google Scholar 

  6. Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., Yuille, A.L.: Detect what you can: detecting and representing objects using holistic models and body parts. In: CVPR, pp. 1979–1986 (2014)

    Google Scholar 

  7. Drews Jr., P., Trujillo, P.N., Rocha, R.P., Campos, M.F.M., Dias, J.: Novelty detection and 3D shape retrieval using superquadrics and multi-scale sampling for autonomous mobile robots. In: ICRA, pp. 3635–3640 (2010)

    Google Scholar 

  8. Duncan, K., Sarkar, S., Alqasemi, R., Dubey, R.: Multi-scale superquadric fitting for efficient shape and pose recovery of unknown objects. In: ICRA, pp. 4238–4243 (2013)

    Google Scholar 

  9. Krivic, J., Solina, F.: Part-level object recognition using superquadrics. CVIU 95(1), 105–126 (2004)

    Google Scholar 

  10. Shi, L., Cheng, I., Basu, A.: Anatomy preserving 3D model decomposition based on robust skeleton-surface node correspondence. In: International Conference on Multimedia and Expo, pp. 1–6, July 2011

    Google Scholar 

  11. Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera, vol. 36 (2017). http://gvv.mpi-inf.mpg.de/projects/VNect/

    Article  Google Scholar 

  12. Moré, J.J.: The Levenberg-Marquardt algorithm: Implementation and theory. In: Watson, G.A. (ed.) Numerical Analysis. LNM, vol. 630, pp. 105–116. Springer, Heidelberg (1978). https://doi.org/10.1007/BFb0067700

    Chapter  Google Scholar 

  13. Lee, M.W., Cohen, I.: A model-based approach for estimating human 3D poses in static images. Trans. Pattern Anal. Mach. Intell. 28(6), 905–916 (2006)

    Article  Google Scholar 

  14. Nekrasov, V., Shen, C., Reid, I.D.: Light-weight refinenet for real-time semantic segmentation. In: BMVC (2018)

    Google Scholar 

  15. Paschalidou, D., Ulusoy, A.O., Geiger, A.: Superquadrics revisited: learning 3D shape parsing beyond cuboids. In: CVPR (2019)

    Google Scholar 

  16. Shotton, J., et al.: Real-time human pose recognition in parts from single depth images. In: CVPR, pp. 1297–1304, June 2011

    Google Scholar 

  17. Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, NIPS 2014, vol. 1, pp. 568–576 (2014)

    Google Scholar 

  18. Solina, F., Bajcsy, R.: Range image interpretation of mail pieces with superquadrics. In: AAAI, pp. 733–737 (1987)

    Google Scholar 

  19. Sundaresan, A., Chellappa, R.: Model driven segmentation of articulating humans in laplacian eigenspace. IEEE Trans. Pattern Anal. Mach. Intell. 30, 1771–85 (2008)

    Article  Google Scholar 

  20. Vaskevicius, N., Birk, A.: Revisiting superquadric fitting: a numerically stable formulation. IEEE Trans. Pattern Anal. Mach. Intell. 41(1), 220–233 (2019)

    Article  Google Scholar 

Download references

Acknowledgement

This work was supported by AIP-PRISM, Japan Science and Technology Agency, Grant Number JPMJCR18Y2, Japan.

Author information

Authors and Affiliations

  1. Keio University, Yokohama, Kanagawa, Japan

    Ryo Hachiuma & Hideo Saito

Authors
  1. Ryo Hachiuma
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hideo Saito
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ryo Hachiuma .

Editor information

Editors and Affiliations

  1. LIMSI-CNRS, University of Paris-Sud, Orsay, France

    Patrick Bourdot

  2. University of Minnesota, Minneapolis, MN, USA

    Victoria Interrante

  3. Federal University of Rio Grande do Sul, Porto Alegre, Brazil

    Luciana Nedel

  4. University of Geneva, Geneva, Switzerland

    Nadia Magnenat-Thalmann

  5. University of Bremen, Bremen, Germany

    Gabriel Zachmann

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Hachiuma, R., Saito, H. (2019). Volumetric Representation of Semantically Segmented Human Body Parts Using Superquadrics. In: Bourdot, P., Interrante, V., Nedel, L., Magnenat-Thalmann, N., Zachmann, G. (eds) Virtual Reality and Augmented Reality. EuroVR 2019. Lecture Notes in Computer Science(), vol 11883. Springer, Cham. https://doi.org/10.1007/978-3-030-31908-3_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-31908-3_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-31907-6

  • Online ISBN: 978-3-030-31908-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation